PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8934 - 8943
• Main Authors: Sun, Deqing, Yang, Xiaodong, Liu, Ming-Yu, Kautz, Jan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Adaptive optics; Benchmark testing; Computational modeling; Computer vision; Feature extraction; Optical imaging; Task analysis
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2018.00931

We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the current optical flow estima...